Optimizing Traffic Signal Control Using Machine Learning and Environmental Data

Abstract

Traffic signal control is a critical component of urban transportation management, and optimizing its performance can significantly reduce congestion, decrease travel times, and improve air quality. This study proposes a novel approach to optimizing traffic signal control using machine learning and environmental data. This work focuses on the interplay between smart city infrastructure and environmental data to provide a novel method for traffic pattern prediction. Mitigating traffic congestion is a pressing concern in urbanized societies and emerging smart cities. This study explores leveraging publicly available air pollution data as an environmental indicator to enhance urban mobility and predict traffic patterns. Taking into account factors including vehicle emissions, weather patterns, and topographical features, the study will look at possible connections between air pollution and traffic congestion. The goal of this project is to develop a prediction model that uses real-time air quality data for traffic forecasting by utilizing big data analytics and machine learning approaches. According to our research, the K-nearest neighbors (KNN) model performs better than any other regression model examined. According to experimental findings, the KNN model considerably lowers the error rate in traffic congestion prediction by over 30%.